diff --git a/scripts/plotting/mcsm_mean_affinity_ensemble.R b/scripts/plotting/mcsm_mean_affinity_ensemble.R
index 7416a27..35b67b4 100644
--- a/scripts/plotting/mcsm_mean_affinity_ensemble.R
+++ b/scripts/plotting/mcsm_mean_affinity_ensemble.R
@@ -103,7 +103,7 @@ cols_to_extract  = cols_to_consider[cols_to_consider%in%c(common_cols
 # Ensemble affinity
 #####################
 # extract outcome cols and map numeric values to the categories
-# Destabilising == 1, and stabilising == 0
+# Destabilising == 0, and stabilising == 1 so rescaling can let -1 be destabilising
 df3_plot = df3[, cols_to_extract]
 
 df3_plot[, outcome_cols_aff] <- sapply(df3_plot[, outcome_cols_aff]
diff --git a/scripts/plotting/mcsm_mean_stability_ensemble.R b/scripts/plotting/mcsm_mean_stability_ensemble.R
index baba72d..6d63764 100644
--- a/scripts/plotting/mcsm_mean_stability_ensemble.R
+++ b/scripts/plotting/mcsm_mean_stability_ensemble.R
@@ -84,8 +84,12 @@ outcome_cols_aff = c("duet_outcome"
                      #,"provean_outcome"
                      #,"snap2_outcome"
 )
-cols_to_consider = colnames(df3)[colnames(df3)%in%c(common_cols, scaled_cols,outcome_cols)]
-cols_to_extract  = cols_to_consider[cols_to_consider%in%c(common_cols, outcome_cols)]
+cols_to_consider = colnames(df3)[colnames(df3)%in%c(common_cols
+                                                    , scaled_cols
+                                                    , outcome_cols)]
+
+cols_to_extract  = cols_to_consider[cols_to_consider%in%c(common_cols
+                                                          , outcome_cols)]
 
 ##############################################################
 #####################